heygen

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's required Default Workflow tells the agent to "Write an optimized prompt using prompt-optimizer.md" (SKILL.md), and prompt-optimizer.md explicitly instructs the agent to "Pull data — Research the topic: web search, APIs, internal docs" (i.e., fetch and ingest web content), and assets.md also includes an uploadFromUrl helper that downloads arbitrary HTTPS URLs — together these show the agent will fetch and interpret untrusted third‑party web content which can materially influence prompts and subsequent tool actions.